Artificial Intelligence

Artificial intelligence (AI) is becoming a crucial component of healthcare to help augment physicians and make them more efficient. In medical imaging, it is helping radiologists more efficiently manage PACS worklists, enable structured reporting, auto detect injuries and diseases, and to pull in relevant prior exams and patient data. In cardiology, AI is helping automate tasks and measurements on imaging and in reporting systems, guides novice echo users to improve imaging and accuracy, and can risk stratify patients. AI includes deep learning algorithms, machine learning, computer-aided detection (CAD) systems, and convolutional neural networks. 

hip dysplasia joint socket

Researchers have developed deep-radiomics-based models capable of predicting osteoporosis with high accuracy and without need for DXA imaging. 

Novice medical professionals perform diagnostic quality echocardiograms with AI guidance 

In a blind pilot study, inexperienced users successfully captured images for 100% of patients using AI guidance.

Even patients who were never hospitalized for COVID-19 face a heightened risk of cardiovascular issues. #longcovid

Authors of the study noted that using the algorithm eliminates the issue of subjectivity and time-consuming visual assessments of emphysema.

Artificial intelligence can help make breast cancer screening mammography more accurate.

Combining ensemble AI models with reads from breast radiologists of mixed experience levels can help health systems consistently diagnose malignant architectural distortion on mammography.

neck ultrasound thyroid

After being presented with more than 15,000 images, each DL network yielded results comparable to that of four seasoned radiologists, authors of a new EJR study said.

Experts have developed an artificial intelligence model that can estimate gestational age with accuracy that rivals that of formally trained sonographers completing fetal biometry scans. 

An example of a lung cancer found using low-dose computed tomography (LDCT). Image courtesy of RSNA

Researchers are using radiomics to narrow patient cohorts down to those who are at the greatest risk of poor lung cancer outcomes.

stomach ache

Experts involved in the study suggest their findings could eventually be used to detect pancreatic cancer in its earliest stages when patients are most likely to respond to interventions favorably.

Concussion brain

The model combines clinical data with imaging from head CT scans in individuals with severe traumatic brain injuries to quickly predict 6-month outcomes.

Danish researchers reported in Radiology that an artificial intelligence system was able to interpret more than 114,000 screening mammograms using a reading protocol with high sensitivity and specificity.

Researchers reported that the artificial intelligence system was able to interpret more than 114,000 screening mammograms using a reading protocol with high sensitivity and specificity.

Chest X-ray. Using an explainable artificial intelligence (AI) model, researchers were recently able to accomplish highly accurate labeling on large datasets of publicly available chest radiograph X-rays.. 

A model that can achieve accuracy in line with that of radiologists when labeling open-access datasets could be a key factor to overcoming limitations of artificial intelligence implementation, researchers explained in Nature Communications.

Ultrasound Tech

Experts involved with the study suggested that these findings could be beneficial in the future of ovarian tumor assessment by providing clinical decision making support.

Around the web

In a new analysis, scheduled to be presented at RSNA 2022 in Chicago, researchers have identified enlarged perivascular spaces in the brains of migraine patients. This may be suggestive of waste clearance issues in the central nervous system.

The study's authors explained how MRI results can be used to help identify children with ADHD—and how these findings could be used in the AI algorithms of tomorrow. The team will be presenting its findings at RSNA 2022 in Chicago. 

Haffty offered his perspective on the conference as a whole and previewed his presidential address, which is scheduled for early Sunday evening.

Trimed Popup
Trimed Popup